kvm-s390.c 19.5 KB
Newer Older
1 2 3
/*
 * s390host.c --  hosting zSeries kernel virtual machines
 *
4
 * Copyright IBM Corp. 2008,2009
5 6 7 8 9 10 11 12
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License (version 2 only)
 * as published by the Free Software Foundation.
 *
 *    Author(s): Carsten Otte <cotte@de.ibm.com>
 *               Christian Borntraeger <borntraeger@de.ibm.com>
 *               Heiko Carstens <heiko.carstens@de.ibm.com>
13
 *               Christian Ehrhardt <ehrhardt@de.ibm.com>
14 15 16 17 18
 */

#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/fs.h>
19
#include <linux/hrtimer.h>
20 21 22 23 24
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/slab.h>
25
#include <linux/timer.h>
26 27
#include <asm/lowcore.h>
#include <asm/pgtable.h>
28
#include <asm/nmi.h>
29
#include <asm/system.h>
30
#include "kvm-s390.h"
31 32 33 34 35 36
#include "gaccess.h"

#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU

struct kvm_stats_debugfs_item debugfs_entries[] = {
	{ "userspace_handled", VCPU_STAT(exit_userspace) },
37
	{ "exit_null", VCPU_STAT(exit_null) },
38 39 40 41
	{ "exit_validity", VCPU_STAT(exit_validity) },
	{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
	{ "exit_external_request", VCPU_STAT(exit_external_request) },
	{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
42 43 44
	{ "exit_instruction", VCPU_STAT(exit_instruction) },
	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
45
	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
46 47 48 49 50 51 52 53 54
	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
	{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
	{ "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) },
	{ "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) },
	{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
	{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
	{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
	{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
55 56 57 58 59 60 61 62 63
	{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
	{ "instruction_spx", VCPU_STAT(instruction_spx) },
	{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
	{ "instruction_stap", VCPU_STAT(instruction_stap) },
	{ "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
64 65 66 67 68 69
	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
	{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
	{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
	{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
70
	{ "diagnose_44", VCPU_STAT(diagnose_44) },
71 72 73
	{ NULL }
};

74
static unsigned long long *facilities;
75 76

/* Section: not file related */
77
int kvm_arch_hardware_enable(void *garbage)
78 79
{
	/* every s390 is virtualization enabled ;-) */
80
	return 0;
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119
}

void kvm_arch_hardware_disable(void *garbage)
{
}

int kvm_arch_hardware_setup(void)
{
	return 0;
}

void kvm_arch_hardware_unsetup(void)
{
}

void kvm_arch_check_processor_compat(void *rtn)
{
}

int kvm_arch_init(void *opaque)
{
	return 0;
}

void kvm_arch_exit(void)
{
}

/* Section: device related */
long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	if (ioctl == KVM_S390_ENABLE_SIE)
		return s390_enable_sie();
	return -EINVAL;
}

int kvm_dev_ioctl_check_extension(long ext)
{
120 121
	int r;

122
	switch (ext) {
123 124 125
	case KVM_CAP_S390_PSW:
		r = 1;
		break;
126
	default:
127
		r = 0;
128
	}
129
	return r;
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
}

/* Section: vm related */
/*
 * Get (and clear) the dirty memory log for a memory slot.
 */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
			       struct kvm_dirty_log *log)
{
	return 0;
}

long kvm_arch_vm_ioctl(struct file *filp,
		       unsigned int ioctl, unsigned long arg)
{
	struct kvm *kvm = filp->private_data;
	void __user *argp = (void __user *)arg;
	int r;

	switch (ioctl) {
150 151 152 153 154 155 156 157 158
	case KVM_S390_INTERRUPT: {
		struct kvm_s390_interrupt s390int;

		r = -EFAULT;
		if (copy_from_user(&s390int, argp, sizeof(s390int)))
			break;
		r = kvm_s390_inject_vm(kvm, &s390int);
		break;
	}
159
	default:
160
		r = -ENOTTY;
161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190
	}

	return r;
}

struct kvm *kvm_arch_create_vm(void)
{
	struct kvm *kvm;
	int rc;
	char debug_name[16];

	rc = s390_enable_sie();
	if (rc)
		goto out_nokvm;

	rc = -ENOMEM;
	kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
	if (!kvm)
		goto out_nokvm;

	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
	if (!kvm->arch.sca)
		goto out_nosca;

	sprintf(debug_name, "kvm-%u", current->pid);

	kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long));
	if (!kvm->arch.dbf)
		goto out_nodbf;

191 192 193
	spin_lock_init(&kvm->arch.float_int.lock);
	INIT_LIST_HEAD(&kvm->arch.float_int.list);

194 195 196 197 198 199 200 201 202 203 204 205
	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
	VM_EVENT(kvm, 3, "%s", "vm created");

	return kvm;
out_nodbf:
	free_page((unsigned long)(kvm->arch.sca));
out_nosca:
	kfree(kvm);
out_nokvm:
	return ERR_PTR(rc);
}

206 207 208
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
209 210 211 212
	if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
		(__u64) vcpu->arch.sie_block)
		vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
	smp_mb();
213
	free_page((unsigned long)(vcpu->arch.sie_block));
214
	kvm_vcpu_uninit(vcpu);
215 216 217 218 219 220
	kfree(vcpu);
}

static void kvm_free_vcpus(struct kvm *kvm)
{
	unsigned int i;
221
	struct kvm_vcpu *vcpu;
222

223 224 225 226 227 228 229 230 231
	kvm_for_each_vcpu(i, vcpu, kvm)
		kvm_arch_vcpu_destroy(vcpu);

	mutex_lock(&kvm->lock);
	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
		kvm->vcpus[i] = NULL;

	atomic_set(&kvm->online_vcpus, 0);
	mutex_unlock(&kvm->lock);
232 233
}

234 235 236 237
void kvm_arch_sync_events(struct kvm *kvm)
{
}

238 239
void kvm_arch_destroy_vm(struct kvm *kvm)
{
240
	kvm_free_vcpus(kvm);
241
	kvm_free_physmem(kvm);
242
	free_page((unsigned long)(kvm->arch.sca));
243
	debug_unregister(kvm->arch.dbf);
244 245 246 247 248 249 250 251 252 253 254
	kfree(kvm);
}

/* Section: vcpu related */
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
	return 0;
}

void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
255
	/* Nothing todo */
256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	save_fp_regs(&vcpu->arch.host_fpregs);
	save_access_regs(vcpu->arch.host_acrs);
	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
	restore_fp_regs(&vcpu->arch.guest_fpregs);
	restore_access_regs(vcpu->arch.guest_acrs);
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
	save_fp_regs(&vcpu->arch.guest_fpregs);
	save_access_regs(vcpu->arch.guest_acrs);
	restore_fp_regs(&vcpu->arch.host_fpregs);
	restore_access_regs(vcpu->arch.host_acrs);
}

static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
{
	/* this equals initial cpu reset in pop, but we don't switch to ESA */
	vcpu->arch.sie_block->gpsw.mask = 0UL;
	vcpu->arch.sie_block->gpsw.addr = 0UL;
	vcpu->arch.sie_block->prefix    = 0UL;
	vcpu->arch.sie_block->ihcpu     = 0xffff;
	vcpu->arch.sie_block->cputm     = 0UL;
	vcpu->arch.sie_block->ckc       = 0UL;
	vcpu->arch.sie_block->todpr     = 0;
	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
	vcpu->arch.guest_fpregs.fpc = 0;
	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
	vcpu->arch.sie_block->gbea = 1;
}

int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH);
296
	set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests);
297 298
	vcpu->arch.sie_block->ecb   = 2;
	vcpu->arch.sie_block->eca   = 0xC1002001U;
299
	vcpu->arch.sie_block->fac   = (int) (long) facilities;
300 301 302 303
	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
	tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
		     (unsigned long) vcpu);
	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
304
	get_cpu_id(&vcpu->arch.cpu_id);
305
	vcpu->arch.cpu_id.version = 0xff;
306 307 308 309 310 311 312 313 314 315 316 317
	return 0;
}

struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
				      unsigned int id)
{
	struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
	int rc = -ENOMEM;

	if (!vcpu)
		goto out_nomem;

318 319
	vcpu->arch.sie_block = (struct kvm_s390_sie_block *)
					get_zeroed_page(GFP_KERNEL);
320 321 322 323 324 325

	if (!vcpu->arch.sie_block)
		goto out_free_cpu;

	vcpu->arch.sie_block->icpua = id;
	BUG_ON(!kvm->arch.sca);
326 327
	if (!kvm->arch.sca->cpu[id].sda)
		kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
328 329 330
	vcpu->arch.sie_block->scaoh = (__u32)(((__u64)kvm->arch.sca) >> 32);
	vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;

331 332 333
	spin_lock_init(&vcpu->arch.local_int.lock);
	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
334
	spin_lock(&kvm->arch.float_int.lock);
335 336
	kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
	init_waitqueue_head(&vcpu->arch.local_int.wq);
337
	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
338
	spin_unlock(&kvm->arch.float_int.lock);
339

340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428
	rc = kvm_vcpu_init(vcpu, kvm, id);
	if (rc)
		goto out_free_cpu;
	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
		 vcpu->arch.sie_block);

	return vcpu;
out_free_cpu:
	kfree(vcpu);
out_nomem:
	return ERR_PTR(rc);
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
	/* kvm common code refers to this, but never calls it */
	BUG();
	return 0;
}

static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
{
	vcpu_load(vcpu);
	kvm_s390_vcpu_initial_reset(vcpu);
	vcpu_put(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	vcpu_load(vcpu);
	memcpy(&vcpu->arch.guest_gprs, &regs->gprs, sizeof(regs->gprs));
	vcpu_put(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	vcpu_load(vcpu);
	memcpy(&regs->gprs, &vcpu->arch.guest_gprs, sizeof(regs->gprs));
	vcpu_put(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	vcpu_load(vcpu);
	memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs));
	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
	vcpu_put(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	vcpu_load(vcpu);
	memcpy(&sregs->acrs, &vcpu->arch.guest_acrs, sizeof(sregs->acrs));
	memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
	vcpu_put(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	vcpu_load(vcpu);
	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
	vcpu->arch.guest_fpregs.fpc = fpu->fpc;
	vcpu_put(vcpu);
	return 0;
}

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	vcpu_load(vcpu);
	memcpy(&fpu->fprs, &vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
	vcpu_put(vcpu);
	return 0;
}

static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
{
	int rc = 0;

	vcpu_load(vcpu);
	if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
		rc = -EBUSY;
429 430 431 432
	else {
		vcpu->run->psw_mask = psw.mask;
		vcpu->run->psw_addr = psw.addr;
	}
433 434 435 436 437 438 439 440 441 442
	vcpu_put(vcpu);
	return rc;
}

int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
				  struct kvm_translation *tr)
{
	return -EINVAL; /* not implemented yet */
}

J
Jan Kiszka 已提交
443 444
int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
445 446 447 448
{
	return -EINVAL; /* not implemented yet */
}

449 450 451 452 453 454 455 456 457 458 459 460
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	return -EINVAL; /* not implemented yet */
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	return -EINVAL; /* not implemented yet */
}

461 462 463 464 465 466 467
static void __vcpu_run(struct kvm_vcpu *vcpu)
{
	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);

	if (need_resched())
		schedule();

468 469 470
	if (test_thread_flag(TIF_MCCK_PENDING))
		s390_handle_mcck();

C
Carsten Otte 已提交
471 472
	kvm_s390_deliver_pending_interrupts(vcpu);

473 474 475 476 477 478
	vcpu->arch.sie_block->icptcode = 0;
	local_irq_disable();
	kvm_guest_enter();
	local_irq_enable();
	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
		   atomic_read(&vcpu->arch.sie_block->cpuflags));
479 480 481 482
	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
	}
483 484 485 486 487 488 489 490 491 492 493
	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
		   vcpu->arch.sie_block->icptcode);
	local_irq_disable();
	kvm_guest_exit();
	local_irq_enable();

	memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16);
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
494
	int rc;
495 496 497 498
	sigset_t sigsaved;

	vcpu_load(vcpu);

499
rerun_vcpu:
500 501 502 503
	if (vcpu->requests)
		if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
			kvm_s390_vcpu_set_mem(vcpu);

504
	/* verify, that memory has been registered */
505
	if (!vcpu->arch.sie_block->gmslm) {
506
		vcpu_put(vcpu);
507
		VCPU_EVENT(vcpu, 3, "%s", "no memory registered to run vcpu");
508 509 510
		return -EINVAL;
	}

511 512 513 514 515
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);

516 517
	BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);

518 519 520
	switch (kvm_run->exit_reason) {
	case KVM_EXIT_S390_SIEIC:
	case KVM_EXIT_UNKNOWN:
521
	case KVM_EXIT_INTR:
522 523 524 525 526 527
	case KVM_EXIT_S390_RESET:
		break;
	default:
		BUG();
	}

528 529 530
	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;

531
	might_fault();
532 533 534 535 536 537

	do {
		__vcpu_run(vcpu);
		rc = kvm_handle_sie_intercept(vcpu);
	} while (!signal_pending(current) && !rc);

538 539 540
	if (rc == SIE_INTERCEPT_RERUNVCPU)
		goto rerun_vcpu;

541 542
	if (signal_pending(current) && !rc) {
		kvm_run->exit_reason = KVM_EXIT_INTR;
543
		rc = -EINTR;
544
	}
545 546 547 548 549 550 551 552 553 554 555 556 557 558 559

	if (rc == -ENOTSUPP) {
		/* intercept cannot be handled in-kernel, prepare kvm-run */
		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
		rc = 0;
	}

	if (rc == -EREMOTE) {
		/* intercept was handled, but userspace support is needed
		 * kvm_run has been prepared by the handler */
		rc = 0;
	}
560

561 562 563
	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;

564 565 566 567 568 569
	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);

	vcpu_put(vcpu);

	vcpu->stat.exit_userspace++;
570
	return rc;
571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
}

static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from,
		       unsigned long n, int prefix)
{
	if (prefix)
		return copy_to_guest(vcpu, guestdest, from, n);
	else
		return copy_to_guest_absolute(vcpu, guestdest, from, n);
}

/*
 * store status at address
 * we use have two special cases:
 * KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit
 * KVM_S390_STORE_STATUS_PREFIXED: -> prefix
 */
int __kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
{
	const unsigned char archmode = 1;
	int prefix;

	if (addr == KVM_S390_STORE_STATUS_NOADDR) {
		if (copy_to_guest_absolute(vcpu, 163ul, &archmode, 1))
			return -EFAULT;
		addr = SAVE_AREA_BASE;
		prefix = 0;
	} else if (addr == KVM_S390_STORE_STATUS_PREFIXED) {
		if (copy_to_guest(vcpu, 163ul, &archmode, 1))
			return -EFAULT;
		addr = SAVE_AREA_BASE;
		prefix = 1;
	} else
		prefix = 0;

606
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
607 608 609
			vcpu->arch.guest_fpregs.fprs, 128, prefix))
		return -EFAULT;

610
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs),
611 612 613
			vcpu->arch.guest_gprs, 128, prefix))
		return -EFAULT;

614
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw),
615 616 617
			&vcpu->arch.sie_block->gpsw, 16, prefix))
		return -EFAULT;

618
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, pref_reg),
619 620 621 622
			&vcpu->arch.sie_block->prefix, 4, prefix))
		return -EFAULT;

	if (__guestcopy(vcpu,
623
			addr + offsetof(struct save_area, fp_ctrl_reg),
624 625 626
			&vcpu->arch.guest_fpregs.fpc, 4, prefix))
		return -EFAULT;

627
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, tod_reg),
628 629 630
			&vcpu->arch.sie_block->todpr, 4, prefix))
		return -EFAULT;

631
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, timer),
632 633 634
			&vcpu->arch.sie_block->cputm, 8, prefix))
		return -EFAULT;

635
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, clk_cmp),
636 637 638
			&vcpu->arch.sie_block->ckc, 8, prefix))
		return -EFAULT;

639
	if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
640 641 642 643
			&vcpu->arch.guest_acrs, 64, prefix))
		return -EFAULT;

	if (__guestcopy(vcpu,
644
			addr + offsetof(struct save_area, ctrl_regs),
645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666
			&vcpu->arch.sie_block->gcr, 128, prefix))
		return -EFAULT;
	return 0;
}

static int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
{
	int rc;

	vcpu_load(vcpu);
	rc = __kvm_s390_vcpu_store_status(vcpu, addr);
	vcpu_put(vcpu);
	return rc;
}

long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;

	switch (ioctl) {
667 668 669 670 671 672 673
	case KVM_S390_INTERRUPT: {
		struct kvm_s390_interrupt s390int;

		if (copy_from_user(&s390int, argp, sizeof(s390int)))
			return -EFAULT;
		return kvm_s390_inject_vcpu(vcpu, &s390int);
	}
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696
	case KVM_S390_STORE_STATUS:
		return kvm_s390_vcpu_store_status(vcpu, arg);
	case KVM_S390_SET_INITIAL_PSW: {
		psw_t psw;

		if (copy_from_user(&psw, argp, sizeof(psw)))
			return -EFAULT;
		return kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
	}
	case KVM_S390_INITIAL_RESET:
		return kvm_arch_vcpu_ioctl_initial_reset(vcpu);
	default:
		;
	}
	return -EINVAL;
}

/* Section: memory related */
int kvm_arch_set_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
				struct kvm_memory_slot old,
				int user_alloc)
{
697
	int i;
698
	struct kvm_vcpu *vcpu;
699

700 701 702 703 704 705 706
	/* A few sanity checks. We can have exactly one memory slot which has
	   to start at guest virtual zero and which has to be located at a
	   page boundary in userland and which has to end at a page boundary.
	   The memory in userland is ok to be fragmented into various different
	   vmas. It is okay to mmap() and munmap() stuff in this slot after
	   doing this call at any time */

707
	if (mem->slot)
708 709 710 711 712 713 714 715 716 717 718
		return -EINVAL;

	if (mem->guest_phys_addr)
		return -EINVAL;

	if (mem->userspace_addr & (PAGE_SIZE - 1))
		return -EINVAL;

	if (mem->memory_size & (PAGE_SIZE - 1))
		return -EINVAL;

719 720 721
	if (!user_alloc)
		return -EINVAL;

722
	/* request update of sie control block for all available vcpus */
723 724 725 726
	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
			continue;
		kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP);
727
	}
728 729 730 731

	return 0;
}

732 733 734 735
void kvm_arch_flush_shadow(struct kvm *kvm)
{
}

736 737 738 739 740 741 742
gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
{
	return gfn;
}

static int __init kvm_s390_init(void)
{
743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760
	int ret;
	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE);
	if (ret)
		return ret;

	/*
	 * guests can ask for up to 255+1 double words, we need a full page
	 * to hold the maximum amount of facilites. On the other hand, we
	 * only set facilities that are known to work in KVM.
	 */
	facilities = (unsigned long long *) get_zeroed_page(GFP_DMA);
	if (!facilities) {
		kvm_exit();
		return -ENOMEM;
	}
	stfle(facilities, 1);
	facilities[0] &= 0xff00fff3f0700000ULL;
	return 0;
761 762 763 764
}

static void __exit kvm_s390_exit(void)
{
765
	free_page((unsigned long) facilities);
766 767 768 769 770
	kvm_exit();
}

module_init(kvm_s390_init);
module_exit(kvm_s390_exit);